Yanghua Jin

1. Currently, Crypko is a pure single page application built on Vue, which means all meta tags in card pages are rendered by client-side javascript engines. However, most SNS crawlers...

Are you using chainer 2? This code only support chainer 1.16~1.24, please downgrade chainer or modify the code manually (http://docs.chainer.org/en/stable/upgrade.html)

Hi, Satoshi Thank you for your interest. Upload scripts [here](https://drive.google.com/file/d/0Bx_f0Ep2RFzhZHJMV1haWW5KaU0/view?usp=sharing). Check [illustration2vec](http://illustration2vec.net/) for tag prediction.

Thanks for your interests. There are two considerations. From the model perspective, obviously, 128x128 pix is too low, I am working on the high-resolution face model now. But the training...

We described our attempts of generating high-resolution images in the paper. In our situation, the limitation of the resolution mainly comes from the training dataset. Personally, I don't think waifu2x...

@shaform I used images larger than 80*80 in the original 42000 faces. Personally, I think 1.5x upsampling is still affordable.

@shaform Yes, but one fundamental problem for building large and high-quality anime face dataset is that lbpcascade_animeface, the only anime face detection library available online, uses old-fashioned methods and has...

In [sampling.py](https://github.com/pfnet-research/chainer-stylegan/blob/master/src/stylegan/sampling.py), if you set `--gpu -1`, the model will be loaded to CPU.

Uploaded to https://drive.google.com/open?id=1Yde3i7knsJ3JK9nZ_oHngvweQODFVLD6 Run `python sampling.py --m_style SmoothedGenerator_405000.npz --m_mapping SmoothedMapping_405000.npz --gpu -1` to sample images